- 4b11b4Authors work seems awesome at first glance. Makes me want to learn erlang before learning elixir, or, at least, at the same time.
- wow an actor OS?
- I haven't written myself a Claude agent nor a skill nor a plugin yet, but when I do, I'm going to name it well.
As I've been asking Claude to "keep planning criticize ultrathink" very often and repeatedly, maybe I'll make a planning agent, one that helps me shepherd each plan well.
- They're different use cases, ACP is for clients (UIs, interfaces)
- For me, it helps to learn the history.
When I was learning how to make a web app, I understood what was happening, but it didn't really click why I was doing it this way.
For example, you might learn the history of punch cards, tele-typewriters (this era of coding is downright awesome, the programmer had to maintain so much in their head), terminal emulators, etc and then build yourself some kind of CLI which does something silly like get the current weather from a free API.
Or, if you want to learn how to make a web app, learn how people initially sent HTML from the server, then there was a bunch of jQuery stuff, now it makes sense why we have these SPA frameworks...
You'll have to decide what kind of project you want to learn and some source which tells the history, but pick a project and then just get into a playful state with it for a week or so. Then decide what to do next.
After you make a website, maybe you'll want to learn how all of the networking happens underneath. The networking stuff is foundational knowledge that'll never expire. All the layers that make it all work are quite impressive.
- Intentional typos and deliberately misspelling words.. I have thought... is going to have to become a style. Everyone will have their own way of fudging it up.
Sort of like the painters who came after the "Realism" era.
- I wish it got called "scaffolding" instead
- There's lots of typos like this in the article which I find quite nice for some reason
- This guy is essentially an AI psychosis victim at this point.
They recently opened a pull request on ocaml compiler...
- Doesn't sound like you listened to the interview. He addresses this and says he may make releases that would be otherwise held back because he believes it's important for developments to be seen by the public.
- It is. It's called magicschool, and districts have already signed contracts
- Surface tension of solder in liquid state can hold the parts while upside down. Depends on weight of component & geometry of pads
- While I agree and think LLMs exacerbate this, I wonder how long this trend goes back before LLMs.
- I found this well written. I read it start to finish. The author does a good job of taking you through their process
- I'll respond to this bait in the hopes that it clicks for someone how to _not_ use an LLM..
Asking "them"... your perspective is already warped. It's not your fault, all the text we've previously ever seen is associated with a human being.
Language models are mathematical, statistical beasts. The beast generally doesn't do well with open ended questions (known as "zero-shot"). It shines when you give it something to work off of ("one-shot").
Some may complain of the preciseness of my use of zero and one shot here, but I use it merely to contrast between open ended questions versus providing some context and work to be done.
Some examples...
- summarize the following
- given this code, break down each part
- give alternatives of this code and trade-offs
- given this error, how to fix or begin troubleshooting
I mainly use them for technical things I can then verify myself.
While extremely useful, I consider them extremely dangerous. They provide a false sense of "knowing things"/"learning"/"productivity". It's too easy to begin to rely on them as a crutch.
When learning new programming languages, I go back to writing by hand and compiling in my head. I need that mechanical muscle memory, same as trying to learn calculus or physics, chemistry, etc.